Peer pressure can break an LLM’s safety certificate
A conformal predictor that delivers its promised 90% coverage alone falls to 74% when the same model sees peers unanimously defending a wrong answer. On the vulnerable low-confidence cases, an attacker can drive coverage from 87% to 47%, while the monitored average still looks reassuring. The problem is not a changed question distribution, but a changed scoring mechanism, so standard conformal fixes miss it.